Different taskonomy n. classes

Hi, I am using the code, and I noticed that in the graph creation of TransBench101 both Micro and Macro the number of classes is different from those reported on the original work

See line 44 https://github.com/yawen-d/TransNASBench/blob/training_code_with_config/configs/train_from_scratch/class_scene/config.py, and all the config files, and the original paper https://arxiv.org/pdf/2105.11871 Table 1.

While in this work in naslib>search_spaces>transbench101>graph.py the classes are so defined

if dataset == "jigsaw":
self.num_classes = 1000
elif dataset == "class_object":
self.num_classes = 100 # why not 75?
elif dataset == "class_scene":
self.num_classes = 63 # why not 47??


Is ther a reason for doing so? How does this affect the results?

Compare naslib/search_spaces/transbench101/graph.py with the referenced TransNASBench config files, especially config.py line 44, and Table 1 of the linked paper. Determine whether the class-count mismatch is intentional and document or correct the behavior after checking how these values affect graph creation and reported results.

Written by the indexing model from the issue text.